Introducing a Nonparametric Model Using k-Nearest Neighbor Technique for Predicting Soil Bulk Density

摘要

Soil bulk density measurements are often required as an input parameter for models that predict soil processes. Nonparametric approaches are being used in various fields to estimate continuous variables. One type of the nonparametric lazy learning algorithms, a k-nearest neighbor (k-NN) algorithm was introduced and tested to estimate soil bulk density from other soil properties, including soil textural fractions, EC, pH, SP, OC and TNV. As many as eight nearest neighbors, based on cross validation technique were selected to perform bulk density prediction from the attributes of 136 soil samples. The nonparametric k-NN technique mostly performed equally well using Pearson correlation coefficient (r=0.86), root-mean-squared errors (RMSE=2.5) maximum error (ME=0.15), coefficient of determination (CD=1.3), modeling efficiency (EF=0.75) and coefficient of residual mass (CRM=0.001) statistics. It can be concluded that the k-NN technique is an alternative to other techniques such as pedotransfer functions (PTFs). Keywords: k-nearest neighbor (k-NN), Soil bulk density, Modeling Full-Text Type of Study: Research | Subject: Ggeneral Received: 2011/10/11 Related Websites Scientific Publications Commission - Health Ministry Scientific Publications Commission - Science Ministry Yektaweb Company Site Keywords ?????, Academic Journal, Scientific Article, ???? ????? ??, ???? ????? ??, ???? ????? ??, ???? ????? ??, ???? ????? ??, ???? ????? ??, ???? ?? Vote ? 2015 All Rights Reserved | JWSS - Isfahan University of Technology